ComfyUI Node
Musubi Cache Latents (Wan)
A ComfyUI node in musubi-tuner/wan/preprocess with 11 inputs and 3 outputs.
Musubi Cache Latents (Wan)
- trigger_in
- dataset_toml_path
- trigger_out
- status_message
◄dataset_config_toml—►
◄vae_name▾►
◄vae_dtypebfloat16►
◄devicecuda►
◄batch_size_override0►
◄num_workers_override0►
◄skip_existingfalse►
◄keep_cachetrue►
◄vae_cache_cpufalse►
◄clip_nameNone►
Categorymusubi-tuner/wan/preprocess
Inputs (11)
| Name | Type | Default | Description |
|---|---|---|---|
| dataset_config_toml | STRING | — | |
| trigger_in | * | — | |
| vae_name | COMBO | VAE Model (Variational AutoEncoder). Select the VAE that is compatible with your base model. The VAE is like the model's "eyes," helping to encode and decode images during the process. | |
| vae_dtype | COMBO | bfloat16 | The data precision type for the VAE (the component that handles images). `bfloat16` is a good option for its balance between speed and quality. |
| device | COMBO | cuda | Choose the hardware device to use for processing. `cuda` uses your NVIDIA GPU (much faster), while `cpu` uses your computer's main processor (much slower). |
| batch_size_override | INT | 0 | Override the default batch size used for processing data. `0` means use the default value from the dataset configuration. A higher number processes more items at once, but uses more memory. |
| num_workers_override | INT | 0 | Override the default number of workers for loading data. `0` means use the default value from the dataset configuration. A higher number can speed up data loading, but consumes more CPU and RAM. |
| skip_existing | BOOLEAN | false | If enabled, the node will skip processing files that already have existing cached versions, saving time and computation. |
| keep_cache | BOOLEAN | true | If enabled, the processed data will be kept in the cache directory even after this operation completes, so it can be reused later without reprocessing. |
| vae_cache_cpu | BOOLEAN | false | If enabled, the VAE's processed outputs will be cached in your system's main memory (RAM) instead of GPU memory. Useful for saving VRAM, especially with large datasets, but can be slower if you have a slow CPU or hard drive. |
| clip_name | COMBO | None | CLIP Model (Vision). If your training is not for "Image-to-Video" (I2V) models, leave it as `None`. If it is I2V, select the appropriate CLIP model, as it helps the model understand the visual information from the input images. |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| dataset_toml_path | STRING | — |
| trigger_out | * | — |
| status_message | STRING | — |